On the Probabilistic Approximation in Reproducing Kernel Hilbert Spaces
Fuente:
arXiv
Salvato in:
| Autori principali: | , |
|---|---|
| Natura: | Preprint |
| Pubblicazione: |
2024
|
| Soggetti: | |
| Accesso online: | |
| Tags: |
Aggiungi Tag
Nessun Tag, puoi essere il primo ad aggiungerne!!
|
| _version_ | 1866916843326799872 |
|---|---|
| author | Chen, Dongwei Wang, Kai-Hsiang |
| author_facet | Chen, Dongwei Wang, Kai-Hsiang |
| contents | This paper studies the probabilistic function approximation problem over reproducing kernel Hilbert spaces. We show the existence and uniqueness of the optimizer under mild assumptions. Furthermore, we generalize the celebrated representer theorem to our setting, and especially when the probability measure is finitely supported, or the Hilbert space is finite-dimensional, we show that the probabilistic approximation problem turns out to be a measure quantization problem, which connects the probabilistic function approximation to the sampling theory. Some discussions and examples are also given when the reproducing kernel Hilbert space is infinite-dimensional and the measure is infinitely supported. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2409_11679 |
| institution | arXiv |
| publishDate | 2024 |
| record_format | arxiv |
| spellingShingle | On the Probabilistic Approximation in Reproducing Kernel Hilbert Spaces Chen, Dongwei Wang, Kai-Hsiang Functional Analysis 46E22 This paper studies the probabilistic function approximation problem over reproducing kernel Hilbert spaces. We show the existence and uniqueness of the optimizer under mild assumptions. Furthermore, we generalize the celebrated representer theorem to our setting, and especially when the probability measure is finitely supported, or the Hilbert space is finite-dimensional, we show that the probabilistic approximation problem turns out to be a measure quantization problem, which connects the probabilistic function approximation to the sampling theory. Some discussions and examples are also given when the reproducing kernel Hilbert space is infinite-dimensional and the measure is infinitely supported. |
| title | On the Probabilistic Approximation in Reproducing Kernel Hilbert Spaces |
| topic | Functional Analysis 46E22 |
| url | https://arxiv.org/abs/2409.11679 |